system

Abstract

We provide the system. [Solution] A natural language processing method that analyzes text and extracts requirements, A database reference means for analyzing similar cases by referring to past proposal data, An automated document generation means that generates an optimal proposal based on extracted requirements and analyzed data, A means for generating a work breakdown diagram for breaking down project tasks after receiving an order, A progress monitoring system that monitors project progress in real time and provides notifications as needed, A system that includes this.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the bidding cases of public institutions and corporate enterprises, a great deal of time and human resources are required for the preparation of proposal documents and project management after bidding. Also, in order to increase the bidding success rate, it is necessary to effectively utilize past successful cases and optimize the proposal documents, but there is a problem that there is no systematic and efficient system for this.

Means for Solving the Problems

[0005] This invention efficiently analyzes the key points of a bidding specification using natural language processing means to analyze text and extract requirements, and analyzes similar cases using a database referencing means that references past proposal data, thereby generating proposals with a high probability of success. Furthermore, it includes an automatic document generation means that generates an optimal proposal based on the extracted requirements and analyzed data, significantly improving the efficiency of proposal creation. In addition, after receiving an order, it uses a work breakdown diagram generation means to break down project tasks, making it easier to manage project progress, and includes a progress monitoring means that monitors project progress in real time and provides notifications as needed, thereby improving the efficiency of project management.

[0006] "Natural language processing techniques" refer to technologies that analyze text and extract specific information or key points.

[0007] "Database referencing means" refers to techniques for extracting and analyzing useful information by searching accumulated historical data.

[0008] "Automated document generation means" refers to technology that automatically creates appropriate documents based on specific input information or requirements.

[0009] "Work breakdown diagram generation method" refers to a technique for clarifying each task in a project and visually showing their priorities and dependencies.

[0010] "Progress monitoring means" refers to technologies that track the progress of a project in real time and provide necessary information based on the progress data. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0022] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0024] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0025] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0031] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0032] This invention provides a method for streamlining proposal creation and project management using an integrated AI system specifically designed for bidding projects by public institutions and corporations. Specific embodiments of the system are described below.

[0033] First, the user inputs information into the system via a terminal, based on the bidding specifications provided by the public institution. This initiates the proposal creation process.

[0034] The server analyzes the received specifications using natural language processing to extract the most important requirements and keywords. In this process, it extracts technical requirements and readily usable functions, and also analyzes interface specifications for integration with other systems.

[0035] Next, the server uses a database of past bidding projects to search for similar projects and identify common elements of successful proposals. This makes it possible to find key points and effective strategies to include in a new proposal.

[0036] Next, the server uses this information to generate a proposal that highlights the company's resources and technical capabilities, employing an automated document generation system. This proposal clearly outlines the project's objectives, methodology, timeline, and the company's competitive advantages.

[0037] This proposal is reviewed by the user via their terminal, and revisions are made as needed. This process ensures that the most persuasive and optimal proposal is finalized. In addition, if the proposal is accepted, the server will initiate project management by configuring tasks via a work breakdown diagram generation mechanism, prioritizing each task, and allocating corresponding resources.

[0038] As the project progresses, the server tracks its progress in real time using progress monitoring tools. If delays or risks are detected in the progress according to pre-defined criteria, the server sends an alert to the user to prompt a quick response.

[0039] As a concrete example, consider a case where an IT company participates in a bid for a "data management system development project." The server extracts requirements such as "cloud technology," "high availability," and "scalability" from the specifications, and identifies elements such as "rapid data migration" and "completion within budget" from past success stories. Based on these, it creates a proposal and automatically formulates a project management plan.

[0040] This invention enables companies to efficiently handle bidding projects and significantly improve the accuracy of project management.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] Users upload the bidding specifications provided by public institutions in electronic format to their terminals and input the data into the system.

[0044] Step 2:

[0045] The server analyzes the bid specifications received from the user using natural language processing techniques and extracts key requirements and keywords from the specifications. For example, it identifies technical requirements and project objectives.

[0046] Step 3:

[0047] The server uses database referencing to search the database of past bids and identify bids similar to the requirements of the extracted specifications. It then analyzes commonalities in the strategies and proposals of past successful bids.

[0048] Step 4:

[0049] Based on extracted requirements and historical data, the server uses automated document generation to create a proposal that effectively showcases the company's resources and technology. The generated proposal clearly outlines the project's progress and the roles and responsibilities of the employees.

[0050] Step 5:

[0051] The user reviews the proposal generated by the server on their terminal, makes manual corrections or additional comments as needed, and then finalizes the proposal.

[0052] Step 6:

[0053] After the proposal is accepted, the server uses a work breakdown diagram generation tool to visually define each task in the project and automatically determine its timeline and resource allocation.

[0054] Step 7:

[0055] The server uses progress monitoring tools to track project status in real time during project execution. If progress is behind schedule or a risk arises, it sends appropriate notifications to the user to prompt action.

[0056] (Example 1)

[0057] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] Public institutions and corporations face challenges in the efficiency of proposal preparation and project management when participating in bidding processes. Manual requirements analysis and searching for similar projects are time-consuming and labor-intensive, and progress monitoring during project execution is insufficient. Furthermore, optimizing resource allocation is difficult, potentially impairing the overall performance of the project.

[0059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0060] In this invention, the server includes information processing means for analyzing text and extracting requirements, data retrieval means for analyzing similar cases by referring to past case data, and document creation means for generating an optimal document based on the extracted requirements and analyzed data. This makes it possible to streamline the proposal creation and project management processes and improve a company's bidding activities and project execution capabilities.

[0061] "Information processing means" refers to technology for analyzing input text data and extracting necessary requirements.

[0062] A "data retrieval method" is a method for identifying and analyzing similar cases by referring to a database of past cases.

[0063] A "document creation method" is a system that automatically generates optimal proposals and documents based on analyzed requirements and data.

[0064] A "diagram generation method" is a technique that breaks down a project into smaller business units and creates diagrams that show the flow and relationships of each business unit.

[0065] A "progress management system" is a function that monitors the progress of a project in real time and notifies users if there are any problems.

[0066] "Resource allocation methods" refer to methods for allocating a company's resources in the most optimal way, based on project requirements.

[0067] An "operation screen" is an interface that allows users to interact with the system and review and modify documents.

[0068] This invention is an integrated system for public institutions and corporations to streamline the creation of proposals and project management for bidding projects. The system comprises information processing means, data retrieval means, document creation means, configuration diagram generation means, progress management means, resource allocation means, and an operation screen.

[0069] First, the user inputs the bidding specifications provided by the public institution into their terminal. The terminal used is a standard computer or tablet device, and the specifications are uploaded in PDF or Word file format.

[0070] The server analyzes the input text data using natural language processing technology. Specifically, it uses software such as SpaCy and NLTK for natural language processing to extract important requirements and keywords. This information processing method makes it easier to identify particularly noteworthy technical and functional requirements within the specifications.

[0071] Next, the server references a database of past cases to identify and analyze similar cases. Using an SQL database, it extracts common elements from past success stories to help create new proposals. By listing similar items and strategies based on the retrieved data, the quality of the proposal is improved.

[0072] The server automatically generates proposals using a generative AI model. For example, it can use OpenAI's GPT model to generate persuasive proposals that highlight a company's resources and technical capabilities. These proposals specifically describe the project's objectives, methodology, timeline, and the company's competitive advantages.

[0073] The generated proposal can be reviewed by the user through an operation screen, and modifications can be made as needed. This operation screen allows the user to manually edit each part of the proposal and confirm the final content.

[0074] If the bid is successful, the server will begin project management and generate a diagram to break down the project into smaller operational units. Project management tools will be used to prioritize and allocate resources to each task, thereby improving operational efficiency.

[0075] During the actual project, the server monitors the project's progress in real time using progress management tools. If delays or risks occur in the progress, the server automatically sends warnings and notifications to the user to prompt a quick response.

[0076] A concrete example is the subject matter of "Tender specifications for the development of a data management system utilizing cloud technology." In this case, a suitable example of a prompt would be, "Generate a proposal based on the following tender specifications: Submit a detailed plan for a project utilizing 'cloud technology'."

[0077] This invention allows companies to drastically streamline the bidding process and significantly improve the effectiveness and efficiency of project management.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The user inputs the bidding specifications provided by the public institution into the terminal. Specifically, they upload the specifications as a PDF or Word file to a dedicated form. The entered data is sent to the system, and it is ready for natural language processing.

[0081] Step 2:

[0082] The server analyzes specification data using a natural language processing engine. Text data is provided as input. This process uses SpaCy or NLTK to tokenize the text and extract key requirements and keywords. This makes it easier to identify technical and functional requirements within the project. The output is a list of extracted requirements.

[0083] Step 3:

[0084] The server references a database of past cases based on the extracted requirements. The input data is the extracted list of requirements. Using an SQL database, it filters similar cases and lists successful examples. This gathers data useful for new proposals. The output is a list of similar cases and their common elements.

[0085] Step 4:

[0086] The server generates a proposal using data from similar projects. The input data consists of a requirements list and elements from similar projects. It utilizes a generation AI model (e.g., a GPT model) to automatically create a proposal that highlights the company's advantages. Specifically, it converts the input data into prompt sentences and feeds them into the AI ​​to generate the document. The output is the automatically generated proposal.

[0087] Step 5:

[0088] The user reviews and modifies the proposal on the user interface. The input data is an automatically generated proposal. The user opens the proposal in a word processor, checks its contents, and manually edits it as needed. Specific actions include correcting text and inserting additional information. The output is the revised proposal.

[0089] Step 6:

[0090] The server begins project management once the proposal is finalized. The input data is the completed proposal. Using a project management tool, it generates a Work Breakdown Structure (WBS) and structures the tasks. Specifically, it prioritizes each task and allocates the necessary resources. The output is a project plan and a list of tasks.

[0091] Step 7:

[0092] The server monitors project progress in real time during the project's execution. The input data is project progress information. Using progress monitoring tools, it tracks ongoing tasks and notifies the user if delays or risks occur. Specific actions include evaluating progress and issuing alerts. The output is delay and risk alert information.

[0093] (Application Example 1)

[0094] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0095] Modern public works and infrastructure projects face increasing complexity in the bidding process and the need for efficient management from the proposal stage to project management. However, traditional methods make it difficult to process vast amounts of information and create proposals that appropriately consider the environment and resources, which is a cause of project delays and failures.

[0096] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0097] In this invention, the server includes a natural language processing means for analyzing text and extracting requirements, a database referencing means for analyzing similar cases by referring to past proposal data, and an automated document generation means for generating an optimal proposal based on the extracted requirements and analyzed data. This enables more efficient proposal creation in public works and infrastructure projects, and optimal allocation of resources in project management.

[0098] "Natural language processing tools" are technologies that analyze text and extract important requirements and keywords from it.

[0099] A "database referencing method" is a technology for searching past proposal data and analyzing similar cases.

[0100] An "automatic document generation method" is a technology that has the function of automatically creating an optimal proposal based on extracted requirements and analyzed data.

[0101] The "configuration diagram generation method" is a technology that breaks down project work in detail after receiving an order, enabling efficient management of the work.

[0102] A "progress monitoring system" is a technology that monitors the progress of a project in real time and provides appropriate notifications according to pre-set criteria.

[0103] "An automated system for creating public works proposals" refers to a technology that quickly and effectively generates proposals while taking into account the specific environmental requirements associated with public works projects.

[0104] A "resource management support configuration" refers to a technology that supports the efficient management and allocation of resources based on project requirements.

[0105] The system for realizing this invention consists of a series of program modules that run on a cloud server. The server is based on Python and uses spaCy and Transformers as natural language processing libraries. This enables natural language processing to extract important requirements from bidding documents for public projects. A SQL-based database is used for database lookups, allowing for high-speed retrieval of past proposal information.

[0106] Automated document generation is performed using a generation AI model based on this extracted and analyzed data, and the proposal reflects environmental requirements and the streamlining of resource management. This process utilizes a database of past project success stories.

[0107] Users access the generated proposals via an interface that allows them to review and modify them as needed, using their terminals. This interface is provided through a user-friendly GUI. As the project progresses, the server automatically generates work breakdown diagrams and manages resource allocation. Real-time progress monitoring is performed using the project management library pm4py, and alerts are automatically sent to the user if progress is behind schedule.

[0108] For example, if a city is bidding on the "implementation of a sustainable energy system," the server can identify key requirements related to energy efficiency from the specifications and quickly create an optimal proposal based on past success stories.

[0109] As an example of a prompt message for a generative AI,

[0110] "To create a proposal for a smart city project, please analyze the bidding specifications, extract key information, and generate an optimal proposal based on past successful case studies."

[0111] These are some examples.

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] Users input the bidding specifications for public projects into the server via their terminals. This input data is uploaded to the server as a text file containing the specifications.

[0115] Step 2:

[0116] The server uses spaCy to analyze the input specification text using natural language processing. This extracts important requirements and keywords from the specification. The input is the text data of the specification, and the output is a list of extracted requirements and keywords.

[0117] Step 3:

[0118] The server references an SQL database to search for proposal data from similar past projects. This identifies common elements from past success stories. The input is a list of extracted requirements, and the output is the past case data found.

[0119] Step 4:

[0120] The server uses a generative AI model to automatically generate documents. This creates a proposal that includes optimal suggestions regarding environmental and resource management. The input is requirements and data from past cases, and the output is the generated proposal document data.

[0121] Step 5:

[0122] The user reviews the generated proposal via the terminal and makes revisions as needed. The input is the generated proposal, and the output is the final version of the proposal reviewed by the user.

[0123] Step 6:

[0124] After the project progresses, the server automatically generates a work breakdown diagram and manages resource allocation based on it. The input is the final proposal, and the output is the configuration diagram and resource management plan.

[0125] Step 7:

[0126] The server uses pm4py to monitor project progress in real time and automatically sends alerts to the user when delays or risks are detected. The input is project progress data, and the output is alert information for the user.

[0127] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0128] This invention combines a system for efficiently and effectively creating proposals for bidding projects by public institutions and corporations with an emotion engine that utilizes user emotions. Specific embodiments of this system are described below.

[0129] In this system, the user first inputs the bid specifications into a terminal and transmits them to the system. The server analyzes this input data using natural language processing to extract the necessary requirements. Next, the server uses a database referencing mechanism to search the database of past bid proposals and identify and analyze similar cases. Based on this information, the server uses an automated document generation mechanism to create the optimal proposal.

[0130] The emotion engine recognizes the user's emotional state and adjusts the content and interface of the proposal based on that. For example, when a user reviews a proposal, the emotion engine uses cameras and sensors to analyze the user's facial expressions and voice, and based on the results, estimates the user's stress level and satisfaction level in real time.

[0131] Using this emotional data, the server dynamically modifies the interface to help users work more comfortably. For example, if a user is emotionally stressed, the system reduces the user's burden by adjusting the layout of proposals to make them easier to read or summarizing the information presented concisely.

[0132] Furthermore, using feedback from the emotion engine, the server makes suggestions to optimize communication among team members even during the project management phase. This process, when combined with real-time progress monitoring during project execution, improves the project's success rate.

[0133] As a concrete example of this system, consider a case where a company participates in a bid to build a large-scale IT system. The server extracts the key points from the specifications and automatically generates a proposal based on past successful examples. At this time, if the emotion engine detects the user's tension or anxiety, it visually highlights important points in the proposal and makes adjustments to help the user understand it.

[0134] Thus, by integrating proposal creation and project management with emotional data, this invention not only improves efficiency but also enhances the user experience based on ergonomics.

[0135] The following describes the processing flow.

[0136] Step 1:

[0137] Users upload the bid specifications in electronic format to their terminals and input the data into the system. This is the starting point of the proposal creation process.

[0138] Step 2:

[0139] The server analyzes the uploaded bid specifications using natural language processing techniques, extracting key requirements and keywords from the specifications. This clarifies the project requirements.

[0140] Step 3:

[0141] The server uses database referencing to search the database of past bidding projects and identify similar projects and their success factors. In this process, it analyzes the characteristics and patterns of past successful proposals.

[0142] Step 4:

[0143] The server uses automated document generation methods to create an optimal proposal that highlights the company's competitive advantages, based on extracted requirements and historical data. The proposal includes project plans and details of technology provision.

[0144] Step 5:

[0145] The user reviews the generated proposal on their device, and the emotion engine acquires emotional data from the user's facial expressions and voice. It then evaluates stress and satisfaction levels and adjusts the interface as needed.

[0146] Step 6:

[0147] The server uses feedback from the emotion engine to dynamically adjust the content and interface of the proposal. For example, if a user experiences stress, improvements such as redisplaying information in a more concise manner are made.

[0148] Step 7:

[0149] After the proposal is completed, in preparation for the project being awarded, the server uses a work breakdown diagram generation mechanism to visually define the project tasks and automatically determines the priority and resource allocation for each task.

[0150] Step 8:

[0151] After the project starts, the server monitors the project's progress in real time using progress monitoring tools and provides feedback using an emotion engine to improve team communication. Notifications are sent to the user as needed.

[0152] (Example 2)

[0153] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0154] In today's competitive environment, companies and public institutions need to prepare bid proposals quickly and effectively. However, proposal preparation is often complex and time-consuming, requiring the effective use of data from past projects and the provision of a user-friendly work environment. Traditional systems have struggled to comprehensively meet these requirements.

[0155] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0156] In this invention, the server includes a natural language processing means for analyzing text and extracting requirements, a database referencing means for analyzing similar cases by referring to past proposal data, an automatic document generation means for generating an optimal document based on the extracted requirements and analyzed data, an emotion engine means for recognizing the user's emotional state and dynamically adjusting the document content and operation screen based on the results, and a progress monitoring means for monitoring project progress in real time and providing notifications as needed. This enables an efficient and user-friendly proposal creation process and improves the effectiveness of project management.

[0157] "Natural language processing methods" are technologies that analyze input text data and extract specific requirements or information from it. Specifically, they obtain information through methods such as word tokenization, part-of-speech tagging, and semantic analysis.

[0158] A "database referencing method" refers to a technique or technology for extracting and analyzing necessary information from storage devices that hold historical data. It is used when searching for and analyzing similar cases.

[0159] An "automatic document generation method" is a technology for automatically generating documents with a specific format and content based on input data. It can be used to create proposals and other documents using natural language generation technology.

[0160] An "emotional engine" is a system that analyzes data such as the user's facial expressions and voice to infer the user's emotional state. Based on this information, it is possible to adjust the interface and change the way documents are presented.

[0161] "Progress monitoring means" refers to technologies and tools for tracking project progress in real time and providing necessary notifications and feedback. They have the function of continuously monitoring the project towards its success.

[0162] This invention provides a system for companies and public institutions to smoothly and effectively create bid proposals and manage projects. Users input bid specifications into their terminals and transfer the digital data to a server. The server analyzes the specifications using natural language processing and extracts the necessary requirements. For this natural language processing, Python's NLTK and spaCy are used as the software to rely on.

[0163] Next, the server uses a database lookup mechanism to search a database containing past similar cases. Common SQL servers or NoSQL databases are often used for database management. Based on the retrieved information, the server uses a generative AI model to automatically generate the optimal proposal. Examples of generative AI models used here include large-scale language models.

[0164] Furthermore, the emotion engine analyzes the user's facial expressions and voice in real time as they review proposals. This utilizes camera sensors and microphones, employing facial recognition APIs and voice analysis tools. Based on the emotion data, the server dynamically adjusts the interface display to support a comfortable user experience. If the user is experiencing stress, the document layout can be adjusted, and important information can be highlighted.

[0165] As a concrete example, consider a case where an organization participates in a bid to build a large-scale IT system. The server analyzes the specifications and generates an optimal proposal based on past successes. Then, content adjustments are made to accommodate the user's preferences. With such a system, the user can obtain efficient and high-quality results in proposal creation.

[0166] Examples of prompt messages include: "Based on the following specifications, please generate a company bid proposal, referencing past success stories. Consider user sentiment data and highlight key points." This information allows users to make quick decisions and increase their chances of successful bidding.

[0167] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0168] Step 1:

[0169] The user enters the bidding specifications into a terminal and sends the digital data to the server. In this input step, the specifications are usually uploaded in PDF or Word format and transferred to the server. As output, the digital data of the bidding specifications is saved on the server.

[0170] Step 2:

[0171] The server analyzes the received bid specifications using natural language processing. Specifically, it tokenizes the input text data, tags it with parts of speech, and extracts important requirements from the specifications. The input is digital data sent from the terminal, and the output is a list of requirements.

[0172] Step 3:

[0173] The server references past proposal data and uses database lookup mechanisms to analyze similar cases. It issues SQL queries to extract highly relevant cases and analyzes their success factors. The input is a list of extracted requirements, and the output is the analysis results of similar cases.

[0174] Step 4:

[0175] The server uses a generation AI model to automatically generate documents based on extracted requirements and analysis results. It generates the optimal proposal using prompt messages. The input is the analysis results of similar cases, and the output is a draft proposal. These prompt messages are sent to the generation AI model in the format of "Please generate a proposal based on the following specifications, referring to past successful cases."

[0176] Step 5:

[0177] When a user reviews a proposal, the emotion engine analyzes the user's facial expressions and voice. Based on data collected by cameras and microphones, it infers the user's emotional state. The input is real-time data from the user, and the output is an evaluation of their emotional state.

[0178] Step 6:

[0179] The server dynamically adjusts the content of the proposal and the user interface based on an assessment of the user's emotional state. For example, if the user is feeling stressed, the document layout is changed to make it easier to read. The input is an assessment of the user's emotional state, and the output is the adjusted interface and proposal.

[0180] (Application Example 2)

[0181] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0182] Proposal creation for bidding and project management requires efficiency and effectiveness, as well as flexibility that takes into account human emotions. However, existing systems have problems with insufficient interface adjustments that reflect user emotions and optimization of work efficiency. Therefore, there is a need for technology that improves proposal creation and project progress management while appropriately utilizing user emotions.

[0183] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0184] In this invention, the server includes a language analysis means for analyzing text and extracting requirements, a memory reference means for analyzing similar cases by referring to past proposal information, and an emotion recognition means for detecting the emotional state of the worker and dynamically adjusting work procedures and information presentation based on that emotion. This enables the automatic generation of proposals tailored to the user's emotions and project management in a low-stress environment.

[0185] "Linguistic analysis means" refers to techniques for analyzing input text and extracting structural requirements.

[0186] The "memory device reference means" is a function for searching previously accumulated proposal information and identifying and analyzing similar cases.

[0187] "Automated document creation method" refers to a technology that generates the optimal proposal based on analyzed requirements and similar cases.

[0188] The "diagram generation means" is a function for generating a diagram that visually breaks down project tasks.

[0189] "Monitoring means" refers to technology for monitoring the progress of work in real time and transmitting information as needed.

[0190] "Emotion recognition means" refers to technology that detects the emotional state of a worker from their facial expressions and voice, and adjusts work procedures and information presentation accordingly.

[0191] In this embodiment of the invention, the server uses language analysis means to extract requirements from text entered by the user into the terminal. Furthermore, the storage device reference means identifies and analyzes similar cases based on past proposal information. This enables the automatic creation of the optimal document. In addition, the emotion recognition means detects the emotional state of the worker and dynamically adjusts the work procedure and information presentation as needed.

[0192] The hardware consists of terminal devices equipped with cameras and emotion sensors, while the software includes language analysis libraries for natural language processing and speech analysis software for emotion recognition. Specifically, Python emotion recognition libraries and natural language processing tools are examples. Using these, the server performs data processing and calculations, enabling users to work without stress.

[0193] A concrete example of this system is a factory production line where workers use camera-equipped terminals. When a worker is referring to instructions on how to set up a machine, the system can detect the worker's frustration and automatically simplify the display of procedures and information.

[0194] Example of a prompt:

[0195] "Adjust the procedures for completing the designated process according to the stress levels of the workers."

[0196] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0197] Step 1:

[0198] The server receives text entered by the user on the terminal and extracts requirements using language analysis tools. The input for this step is the text entered by the user, and the output is the extracted requirements. This process uses natural language processing algorithms to understand the context and identify the necessary requirements.

[0199] Step 2:

[0200] The server uses a memory access mechanism to search for previously stored proposal information and identifies and analyzes cases similar to the input requirements. The input for this step is the requirements extracted in step 1, and the output is the analysis results of similar cases. A database query is executed to extract relevant proposal data.

[0201] Step 3:

[0202] The server uses an automated document generation system to generate an optimal proposal based on the outputs of Step 1 and Step 2. The input for this step is the analysis results of requirements and similar cases, and the output is a draft proposal. A generative AI model is utilized to generate the document in natural language.

[0203] Step 4:

[0204] The device detects the user's emotional state through its camera and sensors and transmits it to the server. The input for this step is data from the user's facial expressions and voice, and the output is the evaluation of their emotional state. Voice and image analysis software is used to evaluate the emotions.

[0205] Step 5:

[0206] The server adjusts the presentation method and content of the proposal based on the results of the emotion recognition system. The input for this step is the result of the emotional state evaluation, and the output is the adjusted information presentation. For example, if the user is feeling stressed, the layout is changed to highlight important points.

[0207] Step 6:

[0208] The user reviews the proposal provided on the terminal and makes any necessary revisions. The input for this step is the revised proposal, and the output is the final proposal. Revisions are made through a simple drag-and-drop interface.

[0209] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0210] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0211] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0212] [Second Embodiment]

[0213] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0214] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0215] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0216] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0217] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0218] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0219] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0220] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0221] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0222] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0223] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0224] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0225] This invention provides a method for streamlining proposal creation and project management using an integrated AI system specifically designed for bidding projects by public institutions and corporations. Specific embodiments of the system are described below.

[0226] First, the user inputs information into the system via a terminal, based on the bidding specifications provided by the public institution. This initiates the proposal creation process.

[0227] The server analyzes the received specifications using natural language processing to extract the most important requirements and keywords. In this process, it extracts technical requirements and readily usable functions, and also analyzes interface specifications for integration with other systems.

[0228] Next, the server uses a database of past bidding projects to search for similar projects and identify common elements of successful proposals. This makes it possible to find key points and effective strategies to include in a new proposal.

[0229] Next, the server uses this information to generate a proposal that highlights the company's resources and technical capabilities, employing an automated document generation system. This proposal clearly outlines the project's objectives, methodology, timeline, and the company's competitive advantages.

[0230] This proposal is reviewed by the user via their terminal, and revisions are made as needed. This process ensures that the most persuasive and optimal proposal is finalized. In addition, if the proposal is accepted, the server will initiate project management by configuring tasks via a work breakdown diagram generation mechanism, prioritizing each task, and allocating corresponding resources.

[0231] As the project progresses, the server tracks its progress in real time using progress monitoring tools. If delays or risks are detected in the progress according to pre-defined criteria, the server sends an alert to the user to prompt a quick response.

[0232] As a concrete example, consider a case where an IT company participates in a bid for a "data management system development project." The server extracts requirements such as "cloud technology," "high availability," and "scalability" from the specifications, and identifies elements such as "rapid data migration" and "completion within budget" from past success stories. Based on these, it creates a proposal and automatically formulates a project management plan.

[0233] This invention enables companies to efficiently handle bidding projects and significantly improve the accuracy of project management.

[0234] The following describes the processing flow.

[0235] Step 1:

[0236] Users upload the bidding specifications provided by public institutions in electronic format to their terminals and input the data into the system.

[0237] Step 2:

[0238] The server analyzes the bid specifications received from the user using natural language processing techniques and extracts key requirements and keywords from the specifications. For example, it identifies technical requirements and project objectives.

[0239] Step 3:

[0240] The server uses database referencing to search the database of past bids and identify bids similar to the requirements of the extracted specifications. It then analyzes commonalities in the strategies and proposals of past successful bids.

[0241] Step 4:

[0242] Based on extracted requirements and historical data, the server uses automated document generation to create a proposal that effectively showcases the company's resources and technology. The generated proposal clearly outlines the project's progress and the roles and responsibilities of the employees.

[0243] Step 5:

[0244] The user reviews the proposal generated by the server on their terminal, makes manual corrections or additional comments as needed, and then finalizes the proposal.

[0245] Step 6:

[0246] After the proposal is accepted, the server uses a work breakdown diagram generation tool to visually define each task in the project and automatically determine its timeline and resource allocation.

[0247] Step 7:

[0248] The server uses progress monitoring tools to track project status in real time during project execution. If progress is behind schedule or a risk arises, it sends appropriate notifications to the user to prompt action.

[0249] (Example 1)

[0250] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0251] Public institutions and corporations face challenges in the efficiency of proposal preparation and project management when participating in bidding processes. Manual requirements analysis and searching for similar projects are time-consuming and labor-intensive, and progress monitoring during project execution is insufficient. Furthermore, optimizing resource allocation is difficult, potentially impairing the overall performance of the project.

[0252] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0253] In this invention, the server includes information processing means for analyzing text and extracting requirements, data retrieval means for analyzing similar cases by referring to past case data, and document creation means for generating an optimal document based on the extracted requirements and analyzed data. This makes it possible to streamline the proposal creation and project management processes and improve a company's bidding activities and project execution capabilities.

[0254] "Information processing means" refers to technology for analyzing input text data and extracting necessary requirements.

[0255] A "data retrieval method" is a method for identifying and analyzing similar cases by referring to a database of past cases.

[0256] A "document creation method" is a system that automatically generates optimal proposals and documents based on analyzed requirements and data.

[0257] A "diagram generation method" is a technique that breaks down a project into smaller business units and creates diagrams that show the flow and relationships of each business unit.

[0258] A "progress management system" is a function that monitors the progress of a project in real time and notifies users if there are any problems.

[0259] "Resource allocation methods" refer to methods for allocating a company's resources in the most optimal way, based on project requirements.

[0260] An "operation screen" is an interface that allows users to interact with the system and review and modify documents.

[0261] This invention is an integrated system for public institutions and corporations to streamline the creation of proposals and project management for bidding projects. The system comprises information processing means, data retrieval means, document creation means, configuration diagram generation means, progress management means, resource allocation means, and an operation screen.

[0262] First, the user inputs the bidding specifications provided by the public institution into their terminal. The terminal used is a standard computer or tablet device, and the specifications are uploaded in PDF or Word file format.

[0263] The server analyzes the input text data using natural language processing technology. Specifically, it uses software such as SpaCy and NLTK for natural language processing to extract important requirements and keywords. This information processing method makes it easier to identify particularly noteworthy technical and functional requirements within the specifications.

[0264] Next, the server references a database of past cases to identify and analyze similar cases. Using an SQL database, it extracts common elements from past success stories to help create new proposals. By listing similar items and strategies based on the retrieved data, the quality of the proposal is improved.

[0265] The server automatically generates proposals using a generative AI model. For example, it can use OpenAI's GPT model to generate persuasive proposals that highlight a company's resources and technical capabilities. These proposals specifically describe the project's objectives, methodology, timeline, and the company's competitive advantages.

[0266] The generated proposal can be reviewed by the user through an operation screen, and modifications can be made as needed. This operation screen allows the user to manually edit each part of the proposal and confirm the final content.

[0267] If the bid is successful, the server will begin project management and generate a diagram to break down the project into smaller operational units. Project management tools will be used to prioritize and allocate resources to each task, thereby improving operational efficiency.

[0268] During the actual project, the server monitors the project's progress in real time using progress management tools. If delays or risks occur in the progress, the server automatically sends warnings and notifications to the user to prompt a quick response.

[0269] A concrete example is the subject matter of "Tender specifications for the development of a data management system utilizing cloud technology." In this case, a suitable example of a prompt would be, "Generate a proposal based on the following tender specifications: Submit a detailed plan for a project utilizing 'cloud technology'."

[0270] This invention allows companies to drastically streamline the bidding process and significantly improve the effectiveness and efficiency of project management.

[0271] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0272] Step 1:

[0273] The user inputs the bidding specifications provided by the public institution into the terminal. Specifically, they upload the specifications as a PDF or Word file to a dedicated form. The entered data is sent to the system, and it is ready for natural language processing.

[0274] Step 2:

[0275] The server analyzes specification data using a natural language processing engine. Text data is provided as input. This process uses SpaCy or NLTK to tokenize the text and extract key requirements and keywords. This makes it easier to identify technical and functional requirements within the project. The output is a list of extracted requirements.

[0276] Step 3:

[0277] The server references a database of past cases based on the extracted requirements. The input data is the extracted list of requirements. Using an SQL database, it filters similar cases and lists successful examples. This gathers data useful for new proposals. The output is a list of similar cases and their common elements.

[0278] Step 4:

[0279] The server generates a proposal using data from similar cases. The input data is the requirement list and elements of similar cases. Utilize a generation AI model (e.g., GPT model) to automatically create a proposal that emphasizes the company's advantages. As a specific operation, convert the input data into a prompt sentence and generate a document by feeding it into the AI. The output is the automatically generated proposal.

[0280] Step 5:

[0281] The user checks and modifies the proposal on the operation screen. The input data is the automatically generated proposal. Open the proposal on a word processor, check the content, and manually edit it as needed. Specific operations include text correction and insertion of additional information. The output is the revised proposal.

[0282] Step 6:

[0283] When the proposal is finalized, the server starts project management. The input data is the completed proposal. Use a project management tool to generate a work breakdown structure (WBS) and configure tasks. As a specific operation, assign priorities to each task and allocate the necessary resources. The output is the project plan and a list of tasks.

[0284] Step 7:

[0285] The server monitors the progress in real-time during the project. The input data is the project progress information. Use progress monitoring means to track ongoing tasks and notify the user if delays or risks occur. Specific operations include evaluation of the progress status and issuance of alerts. The output is alert information on delays or risks.

[0286] (Application Example 1)

[0287] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0288] Modern public works and infrastructure projects face increasing complexity in the bidding process and the need for efficient management from the proposal stage to project management. However, traditional methods make it difficult to process vast amounts of information and create proposals that appropriately consider the environment and resources, which is a cause of project delays and failures.

[0289] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0290] In this invention, the server includes a natural language processing means for analyzing text and extracting requirements, a database referencing means for analyzing similar cases by referring to past proposal data, and an automated document generation means for generating an optimal proposal based on the extracted requirements and analyzed data. This enables more efficient proposal creation in public works and infrastructure projects, and optimal allocation of resources in project management.

[0291] "Natural language processing tools" are technologies that analyze text and extract important requirements and keywords from it.

[0292] A "database referencing method" is a technology for searching past proposal data and analyzing similar cases.

[0293] An "automatic document generation method" is a technology that has the function of automatically creating an optimal proposal based on extracted requirements and analyzed data.

[0294] The "configuration diagram generation method" is a technology that breaks down project work in detail after receiving an order, enabling efficient management of the work.

[0295] A "progress monitoring system" is a technology that monitors the progress of a project in real time and provides appropriate notifications according to pre-set criteria.

[0296] "An automated system for creating public works proposals" refers to a technology that quickly and effectively generates proposals while taking into account the specific environmental requirements associated with public works projects.

[0297] A "resource management support configuration" refers to a technology that supports the efficient management and allocation of resources based on project requirements.

[0298] The system for realizing this invention consists of a series of program modules that run on a cloud server. The server is based on Python and uses spaCy and Transformers as natural language processing libraries. This enables natural language processing to extract important requirements from bidding documents for public projects. A SQL-based database is used for database lookups, allowing for high-speed retrieval of past proposal information.

[0299] Automated document generation is performed using a generation AI model based on this extracted and analyzed data, and the proposal reflects environmental requirements and the streamlining of resource management. This process utilizes a database of past project success stories.

[0300] Users access the generated proposals via an interface that allows them to review and modify them as needed, using their terminals. This interface is provided through a user-friendly GUI. As the project progresses, the server automatically generates work breakdown diagrams and manages resource allocation. Real-time progress monitoring is performed using the project management library pm4py, and alerts are automatically sent to the user if progress is behind schedule.

[0301] As a specific example, when a certain city conducts a tender for the "introduction of a sustainable energy system", the server can identify the important requirements related to energy efficiency from the specification document and create a quick and optimal proposal based on past successful cases.

[0302] As an example of a prompt sentence for generative AI,

[0303] "Please analyze the tender specification to extract important matters and generate optimal proposal content based on past successful cases in order to create a proposal for a smart city project."

[0304] can be cited.

[0305] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0306] Step 1:

[0307] The user inputs the tender specification of the public project to the server through the terminal. This input data is uploaded to the server as a text file of the specification.

[0308] Step 2:

[0309] The server uses spaCy to analyze the input specification text by natural language processing. As a result, important requirements and keywords are extracted from the specification. The input is the text data of the specification, and the output is a list of the extracted requirements and keywords.

[0310] Step 3:

[0311] The server searches the SQL database for proposal data of past similar projects. As a result, common elements are identified from past successful cases. The input is the list of the extracted requirements, and the output is the found past case data.

[0312] Step 4:

[0313] The server uses a generative AI model to automatically generate documents. This creates a proposal that includes optimal suggestions regarding environmental and resource management. The input is requirements and data from past cases, and the output is the generated proposal document data.

[0314] Step 5:

[0315] The user reviews the generated proposal via the terminal and makes revisions as needed. The input is the generated proposal, and the output is the final version of the proposal reviewed by the user.

[0316] Step 6:

[0317] After the project progresses, the server automatically generates a work breakdown diagram and manages resource allocation based on it. The input is the final proposal, and the output is the configuration diagram and resource management plan.

[0318] Step 7:

[0319] The server uses pm4py to monitor project progress in real time and automatically sends alerts to the user when delays or risks are detected. The input is project progress data, and the output is alert information for the user.

[0320] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0321] This invention combines a system for efficiently and effectively creating proposals for bidding projects by public institutions and corporations with an emotion engine that utilizes user emotions. Specific embodiments of this system are described below.

[0322] In this system, the user first inputs the bid specifications into a terminal and transmits them to the system. The server analyzes this input data using natural language processing to extract the necessary requirements. Next, the server uses a database referencing mechanism to search the database of past bid proposals and identify and analyze similar cases. Based on this information, the server uses an automated document generation mechanism to create the optimal proposal.

[0323] The emotion engine recognizes the user's emotional state and adjusts the content and interface of the proposal based on that. For example, when a user reviews a proposal, the emotion engine uses cameras and sensors to analyze the user's facial expressions and voice, and based on the results, estimates the user's stress level and satisfaction level in real time.

[0324] Using this emotional data, the server dynamically modifies the interface to help users work more comfortably. For example, if a user is emotionally stressed, the system reduces the user's burden by adjusting the layout of proposals to make them easier to read or summarizing the information presented concisely.

[0325] Furthermore, using feedback from the emotion engine, the server makes suggestions to optimize communication among team members even during the project management phase. This process, when combined with real-time progress monitoring during project execution, improves the project's success rate.

[0326] As a concrete example of this system, consider a case where a company participates in a bid to build a large-scale IT system. The server extracts the key points from the specifications and automatically generates a proposal based on past successful examples. At this time, if the emotion engine detects the user's tension or anxiety, it visually highlights important points in the proposal and makes adjustments to help the user understand it.

[0327] Thus, by integrating proposal creation and project management with emotional data, this invention not only improves efficiency but also enhances the user experience based on ergonomics.

[0328] The following describes the processing flow.

[0329] Step 1:

[0330] Users upload the bid specifications in electronic format to their terminals and input the data into the system. This is the starting point of the proposal creation process.

[0331] Step 2:

[0332] The server analyzes the uploaded bid specifications using natural language processing techniques, extracting key requirements and keywords from the specifications. This clarifies the project requirements.

[0333] Step 3:

[0334] The server uses database referencing to search the database of past bidding projects and identify similar projects and their success factors. In this process, it analyzes the characteristics and patterns of past successful proposals.

[0335] Step 4:

[0336] The server uses automated document generation methods to create an optimal proposal that highlights the company's competitive advantages, based on extracted requirements and historical data. The proposal includes project plans and details of technology provision.

[0337] Step 5:

[0338] The user reviews the generated proposal on their device, and the emotion engine acquires emotional data from the user's facial expressions and voice. It then evaluates stress and satisfaction levels and adjusts the interface as needed.

[0339] Step 6:

[0340] The server uses feedback from the emotion engine to dynamically adjust the content and interface of the proposal. For example, if a user experiences stress, improvements such as redisplaying information in a more concise manner are made.

[0341] Step 7:

[0342] After the proposal is completed, in preparation for the project being awarded, the server uses a work breakdown diagram generation mechanism to visually define the project tasks and automatically determines the priority and resource allocation for each task.

[0343] Step 8:

[0344] After the project starts, the server monitors the project's progress in real time using progress monitoring tools and provides feedback using an emotion engine to improve team communication. Notifications are sent to the user as needed.

[0345] (Example 2)

[0346] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0347] In today's competitive environment, companies and public institutions need to prepare bid proposals quickly and effectively. However, proposal preparation is often complex and time-consuming, requiring the effective use of data from past projects and the provision of a user-friendly work environment. Traditional systems have struggled to comprehensively meet these requirements.

[0348] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0349] In this invention, the server includes a natural language processing means for analyzing text and extracting requirements, a database referencing means for analyzing similar cases by referring to past proposal data, an automatic document generation means for generating an optimal document based on the extracted requirements and analyzed data, an emotion engine means for recognizing the user's emotional state and dynamically adjusting the document content and operation screen based on the results, and a progress monitoring means for monitoring project progress in real time and providing notifications as needed. This enables an efficient and user-friendly proposal creation process and improves the effectiveness of project management.

[0350] "Natural language processing methods" are technologies that analyze input text data and extract specific requirements or information from it. Specifically, they obtain information through methods such as word tokenization, part-of-speech tagging, and semantic analysis.

[0351] A "database referencing method" refers to a technique or technology for extracting and analyzing necessary information from storage devices that hold historical data. It is used when searching for and analyzing similar cases.

[0352] An "automatic document generation method" is a technology for automatically generating documents with a specific format and content based on input data. It can be used to create proposals and other documents using natural language generation technology.

[0353] An "emotional engine" is a system that analyzes data such as the user's facial expressions and voice to infer the user's emotional state. Based on this information, it is possible to adjust the interface and change the way documents are presented.

[0354] "Progress monitoring means" refers to technologies and tools for tracking project progress in real time and providing necessary notifications and feedback. They have the function of continuously monitoring the project towards its success.

[0355] This invention provides a system for companies and public institutions to smoothly and effectively create bid proposals and manage projects. Users input bid specifications into their terminals and transfer the digital data to a server. The server analyzes the specifications using natural language processing and extracts the necessary requirements. For this natural language processing, Python's NLTK and spaCy are used as the software to rely on.

[0356] Next, the server uses a database lookup mechanism to search a database containing past similar cases. Common SQL servers or NoSQL databases are often used for database management. Based on the retrieved information, the server uses a generative AI model to automatically generate the optimal proposal. Examples of generative AI models used here include large-scale language models.

[0357] Furthermore, the emotion engine analyzes the user's facial expressions and voice in real time as they review proposals. This utilizes camera sensors and microphones, employing facial recognition APIs and voice analysis tools. Based on the emotion data, the server dynamically adjusts the interface display to support a comfortable user experience. If the user is experiencing stress, the document layout can be adjusted, and important information can be highlighted.

[0358] As a concrete example, consider a case where an organization participates in a bid to build a large-scale IT system. The server analyzes the specifications and generates an optimal proposal based on past successes. Then, content adjustments are made to accommodate the user's preferences. With such a system, the user can obtain efficient and high-quality results in proposal creation.

[0359] Examples of prompt messages include: "Based on the following specifications, please generate a company bid proposal, referencing past success stories. Consider user sentiment data and highlight key points." This information allows users to make quick decisions and increase their chances of successful bidding.

[0360] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0361] Step 1:

[0362] The user enters the bidding specifications into a terminal and sends the digital data to the server. In this input step, the specifications are usually uploaded in PDF or Word format and transferred to the server. As output, the digital data of the bidding specifications is saved on the server.

[0363] Step 2:

[0364] The server analyzes the received bid specifications using natural language processing. Specifically, it tokenizes the input text data, tags it with parts of speech, and extracts important requirements from the specifications. The input is digital data sent from the terminal, and the output is a list of requirements.

[0365] Step 3:

[0366] The server references past proposal data and uses database lookup mechanisms to analyze similar cases. It issues SQL queries to extract highly relevant cases and analyzes their success factors. The input is a list of extracted requirements, and the output is the analysis results of similar cases.

[0367] Step 4:

[0368] The server uses a generation AI model to automatically generate documents based on extracted requirements and analysis results. It generates the optimal proposal using prompt messages. The input is the analysis results of similar cases, and the output is a draft proposal. These prompt messages are sent to the generation AI model in the format of "Please generate a proposal based on the following specifications, referring to past successful cases."

[0369] Step 5:

[0370] When a user reviews a proposal, the emotion engine analyzes the user's facial expressions and voice. Based on data collected by cameras and microphones, it infers the user's emotional state. The input is real-time data from the user, and the output is an evaluation of their emotional state.

[0371] Step 6:

[0372] The server dynamically adjusts the content of the proposal and the user interface based on an assessment of the user's emotional state. For example, if the user is feeling stressed, the document layout is changed to make it easier to read. The input is an assessment of the user's emotional state, and the output is the adjusted interface and proposal.

[0373] (Application Example 2)

[0374] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0375] Proposal creation for bidding and project management requires efficiency and effectiveness, as well as flexibility that takes into account human emotions. However, existing systems have problems with insufficient interface adjustments that reflect user emotions and optimization of work efficiency. Therefore, there is a need for technology that improves proposal creation and project progress management while appropriately utilizing user emotions.

[0376] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0377] In this invention, the server includes a language analysis means for analyzing text and extracting requirements, a memory reference means for analyzing similar cases by referring to past proposal information, and an emotion recognition means for detecting the emotional state of the worker and dynamically adjusting work procedures and information presentation based on that emotion. This enables the automatic generation of proposals tailored to the user's emotions and project management in a low-stress environment.

[0378] "Linguistic analysis means" refers to techniques for analyzing input text and extracting structural requirements.

[0379] The "memory device reference means" is a function for searching previously accumulated proposal information and identifying and analyzing similar cases.

[0380] "Automated document creation method" refers to a technology that generates the optimal proposal based on analyzed requirements and similar cases.

[0381] The "diagram generation means" is a function for generating a diagram that visually breaks down project tasks.

[0382] "Monitoring means" refers to technology for monitoring the progress of work in real time and transmitting information as needed.

[0383] "Emotion recognition means" refers to technology that detects the emotional state of a worker from their facial expressions and voice, and adjusts work procedures and information presentation accordingly.

[0384] In this embodiment of the invention, the server uses language analysis means to extract requirements from text entered by the user into the terminal. Furthermore, the storage device reference means identifies and analyzes similar cases based on past proposal information. This enables the automatic creation of the optimal document. In addition, the emotion recognition means detects the emotional state of the worker and dynamically adjusts the work procedure and information presentation as needed.

[0385] The hardware consists of terminal devices equipped with cameras and emotion sensors, while the software includes language analysis libraries for natural language processing and speech analysis software for emotion recognition. Specifically, Python emotion recognition libraries and natural language processing tools are examples. Using these, the server performs data processing and calculations, enabling users to work without stress.

[0386] A concrete example of this system is a factory production line where workers use camera-equipped terminals. When a worker is referring to instructions on how to set up a machine, the system can detect the worker's frustration and automatically simplify the display of procedures and information.

[0387] Example of a prompt:

[0388] "Adjust the procedures for completing the designated process according to the stress levels of the workers."

[0389] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0390] Step 1:

[0391] The server receives text entered by the user on the terminal and extracts requirements using language analysis tools. The input for this step is the text entered by the user, and the output is the extracted requirements. This process uses natural language processing algorithms to understand the context and identify the necessary requirements.

[0392] Step 2:

[0393] The server uses a memory access mechanism to search for previously stored proposal information and identifies and analyzes cases similar to the input requirements. The input for this step is the requirements extracted in step 1, and the output is the analysis results of similar cases. A database query is executed to extract relevant proposal data.

[0394] Step 3:

[0395] The server uses an automated document generation system to generate an optimal proposal based on the outputs of Step 1 and Step 2. The input for this step is the analysis results of requirements and similar cases, and the output is a draft proposal. A generative AI model is utilized to generate the document in natural language.

[0396] Step 4:

[0397] The device detects the user's emotional state through its camera and sensors and transmits it to the server. The input for this step is data from the user's facial expressions and voice, and the output is the evaluation of their emotional state. Voice and image analysis software is used to evaluate the emotions.

[0398] Step 5:

[0399] The server adjusts the presentation method and content of the proposal based on the results of the emotion recognition system. The input for this step is the result of the emotional state evaluation, and the output is the adjusted information presentation. For example, if the user is feeling stressed, the layout is changed to highlight important points.

[0400] Step 6:

[0401] The user reviews the proposal provided on the terminal and makes any necessary revisions. The input for this step is the revised proposal, and the output is the final proposal. Revisions are made through a simple drag-and-drop interface.

[0402] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0403] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0404] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0405] [Third Embodiment]

[0406] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0407] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0408] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0409] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0410] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0411] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0412] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0413] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0414] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0415] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0416] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0417] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0418] This invention provides a method for streamlining proposal creation and project management using an integrated AI system specifically designed for bidding projects by public institutions and corporations. Specific embodiments of the system are described below.

[0419] First, the user inputs information into the system via a terminal, based on the bidding specifications provided by the public institution. This initiates the proposal creation process.

[0420] The server analyzes the received specifications using natural language processing to extract the most important requirements and keywords. In this process, it extracts technical requirements and readily usable functions, and also analyzes interface specifications for integration with other systems.

[0421] Next, the server uses a database of past bidding projects to search for similar projects and identify common elements of successful proposals. This makes it possible to find key points and effective strategies to include in a new proposal.

[0422] Next, the server uses this information to generate a proposal that highlights the company's resources and technical capabilities using an automated document generation system. This proposal will specifically outline the project's objectives, methodology, timeline, and the company's competitive advantages.

[0423] This proposal is reviewed by the user via their terminal, and revisions are made as needed. This process ensures that the most persuasive and optimal proposal is finalized. In addition, if the proposal is accepted, the server will initiate project management by configuring tasks via a work breakdown diagram generation mechanism, prioritizing each task, and allocating corresponding resources.

[0424] As the project progresses, the server tracks its progress in real time using progress monitoring tools. If delays or risks are detected in the progress according to pre-defined criteria, the server sends an alert to the user to prompt a quick response.

[0425] As a concrete example, consider a case where an IT company participates in a bid for a "data management system development project." The server extracts requirements such as "cloud technology," "high availability," and "scalability" from the specifications, and identifies elements such as "rapid data migration" and "completion within budget" from past success stories. Based on these, it creates a proposal and automatically formulates a project management plan.

[0426] This invention enables companies to efficiently handle bidding projects and significantly improve the accuracy of project management.

[0427] The following describes the processing flow.

[0428] Step 1:

[0429] Users upload the bidding specifications provided by public institutions in electronic format to their terminals and input the data into the system.

[0430] Step 2:

[0431] The server analyzes the bid specifications received from the user using natural language processing techniques and extracts key requirements and keywords from the specifications. For example, it identifies technical requirements and project objectives.

[0432] Step 3:

[0433] The server uses database referencing to search the database of past bids and identify bids similar to the requirements of the extracted specifications. It then analyzes commonalities in the strategies and proposals of past successful bids.

[0434] Step 4:

[0435] Based on extracted requirements and historical data, the server uses automated document generation to create a proposal that effectively showcases the company's resources and technology. The generated proposal clearly outlines the project's progress and the roles and responsibilities of the employees.

[0436] Step 5:

[0437] The user reviews the proposal generated by the server on their terminal, makes manual corrections or additional comments as needed, and then finalizes the proposal.

[0438] Step 6:

[0439] After the proposal is accepted, the server uses a work breakdown diagram generation tool to visually define each task in the project and automatically determine its timeline and resource allocation.

[0440] Step 7:

[0441] The server uses progress monitoring tools to track project status in real time during project execution. If progress is behind schedule or a risk arises, it sends appropriate notifications to the user to prompt action.

[0442] (Example 1)

[0443] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0444] Public institutions and corporations face challenges in the efficiency of proposal preparation and project management when participating in bidding processes. Manual requirements analysis and searching for similar projects are time-consuming and labor-intensive, and progress monitoring during project execution is insufficient. Furthermore, optimizing resource allocation is difficult, potentially impairing the overall performance of the project.

[0445] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0446] In this invention, the server includes information processing means for analyzing text and extracting requirements, data retrieval means for analyzing similar cases by referring to past case data, and document creation means for generating an optimal document based on the extracted requirements and analyzed data. This makes it possible to streamline the proposal creation and project management processes and improve a company's bidding activities and project execution capabilities.

[0447] "Information processing means" refers to technology for analyzing input text data and extracting necessary requirements.

[0448] A "data retrieval method" is a method for identifying and analyzing similar cases by referring to a database of past cases.

[0449] A "document creation method" is a system that automatically generates optimal proposals and documents based on analyzed requirements and data.

[0450] A "diagram generation method" is a technique that breaks down a project into smaller business units and creates diagrams that show the flow and relationships of each business unit.

[0451] A "progress management system" is a function that monitors the progress of a project in real time and notifies users if there are any problems.

[0452] "Resource allocation methods" refer to methods for allocating a company's resources in the most optimal way, based on project requirements.

[0453] An "operation screen" is an interface that allows users to interact with the system and review and modify documents.

[0454] This invention is an integrated system for public institutions and corporations to streamline the creation of proposals and project management for bidding projects. The system comprises information processing means, data retrieval means, document creation means, configuration diagram generation means, progress management means, resource allocation means, and an operation screen.

[0455] First, the user inputs the bidding specifications provided by the public institution into their terminal. The terminal used is a standard computer or tablet device, and the specifications are uploaded in PDF or Word file format.

[0456] The server analyzes the input text data using natural language processing technology. Specifically, it uses software such as SpaCy and NLTK for natural language processing to extract important requirements and keywords. This information processing method makes it easier to identify particularly noteworthy technical and functional requirements within the specifications.

[0457] Next, the server references a database of past cases to identify and analyze similar cases. Using an SQL database, it extracts common elements from past success stories to help create new proposals. By listing similar items and strategies based on the retrieved data, the quality of the proposal is improved.

[0458] The server automatically generates proposals using a generative AI model. For example, it can use OpenAI's GPT model to generate persuasive proposals that highlight a company's resources and technical capabilities. These proposals specifically describe the project's objectives, methodology, timeline, and the company's competitive advantages.

[0459] The generated proposal can be reviewed by the user through an operation screen, and modifications can be made as needed. This operation screen allows the user to manually edit each part of the proposal and confirm the final content.

[0460] If the bid is successful, the server will begin project management and generate a diagram to break down the project into smaller operational units. Project management tools will be used to prioritize and allocate resources to each task, thereby improving operational efficiency.

[0461] During the actual project, the server monitors the project's progress in real time using progress management tools. If delays or risks occur in the progress, the server automatically sends warnings and notifications to the user to prompt a quick response.

[0462] A concrete example is the subject matter of "Tender specifications for the development of a data management system utilizing cloud technology." In this case, a suitable example of a prompt would be, "Generate a proposal based on the following tender specifications: Submit a detailed plan for a project utilizing 'cloud technology'."

[0463] This invention allows companies to drastically streamline the bidding process and significantly improve the effectiveness and efficiency of project management.

[0464] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0465] Step 1:

[0466] The user inputs the bidding specifications provided by the public institution into the terminal. Specifically, they upload the specifications as a PDF or Word file to a dedicated form. The entered data is sent to the system, and it is ready for natural language processing.

[0467] Step 2:

[0468] The server analyzes specification data using a natural language processing engine. Text data is provided as input. This process uses SpaCy or NLTK to tokenize the text and extract key requirements and keywords. This makes it easier to identify technical and functional requirements within the project. The output is a list of extracted requirements.

[0469] Step 3:

[0470] The server references a database of past cases based on the extracted requirements. The input data is the extracted list of requirements. Using an SQL database, it filters similar cases and lists successful examples. This gathers data useful for new proposals. The output is a list of similar cases and their common elements.

[0471] Step 4:

[0472] The server generates a proposal using data from similar projects. The input data consists of a requirements list and elements from similar projects. It utilizes a generation AI model (e.g., a GPT model) to automatically create a proposal that highlights the company's advantages. Specifically, it converts the input data into prompt sentences and feeds them into the AI ​​to generate the document. The output is the automatically generated proposal.

[0473] Step 5:

[0474] The user reviews and modifies the proposal on the user interface. The input data is an automatically generated proposal. The user opens the proposal in a word processor, checks its contents, and manually edits it as needed. Specific actions include correcting text and inserting additional information. The output is the revised proposal.

[0475] Step 6:

[0476] The server begins project management once the proposal is finalized. The input data is the completed proposal. Using a project management tool, it generates a Work Breakdown Structure (WBS) and structures the tasks. Specifically, it prioritizes each task and allocates the necessary resources. The output is a project plan and a list of tasks.

[0477] Step 7:

[0478] The server monitors project progress in real time during the project's execution. The input data is project progress information. Using progress monitoring tools, it tracks ongoing tasks and notifies the user if delays or risks occur. Specific actions include evaluating progress and issuing alerts. The output is delay and risk alert information.

[0479] (Application Example 1)

[0480] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0481] Modern public works and infrastructure projects face increasing complexity in the bidding process and the need for efficient management from the proposal stage to project management. However, traditional methods make it difficult to process vast amounts of information and create proposals that appropriately consider the environment and resources, which is a cause of project delays and failures.

[0482] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0483] In this invention, the server includes a natural language processing means for analyzing text and extracting requirements, a database referencing means for analyzing similar cases by referring to past proposal data, and an automated document generation means for generating an optimal proposal based on the extracted requirements and analyzed data. This enables more efficient proposal creation in public works and infrastructure projects, and optimal allocation of resources in project management.

[0484] "Natural language processing tools" are technologies that analyze text and extract important requirements and keywords from it.

[0485] A "database referencing method" is a technology for searching past proposal data and analyzing similar cases.

[0486] An "automatic document generation method" is a technology that has the function of automatically creating an optimal proposal based on extracted requirements and analyzed data.

[0487] The "configuration diagram generation method" is a technology that breaks down project work in detail after receiving an order, enabling efficient management of the work.

[0488] A "progress monitoring system" is a technology that monitors the progress of a project in real time and provides appropriate notifications according to pre-set criteria.

[0489] "An automated system for creating public works proposals" refers to a technology that quickly and effectively generates proposals while taking into account the specific environmental requirements associated with public works projects.

[0490] A "resource management support configuration" refers to a technology that supports the efficient management and allocation of resources based on project requirements.

[0491] The system for realizing this invention consists of a series of program modules that run on a cloud server. The server is based on Python and uses spaCy and Transformers as natural language processing libraries. This enables natural language processing to extract important requirements from bidding documents for public projects. A SQL-based database is used for database lookups, allowing for high-speed retrieval of past proposal information.

[0492] Automated document generation is performed using a generation AI model based on this extracted and analyzed data, and the proposal reflects environmental requirements and the streamlining of resource management. This process utilizes a database of past project success stories.

[0493] Users access the generated proposals via an interface that allows them to review and modify them as needed, using their terminals. This interface is provided through a user-friendly GUI. As the project progresses, the server automatically generates work breakdown diagrams and manages resource allocation. Real-time progress monitoring is performed using the project management library pm4py, and alerts are automatically sent to the user if progress is behind schedule.

[0494] For example, if a city is bidding on the "implementation of a sustainable energy system," the server can identify key requirements related to energy efficiency from the specifications and quickly create an optimal proposal based on past success stories.

[0495] As an example of a prompt message for a generative AI,

[0496] "To create a proposal for a smart city project, please analyze the bidding specifications, extract key information, and generate an optimal proposal based on past successful case studies."

[0497] These are some examples.

[0498] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0499] Step 1:

[0500] Users input the bidding specifications for public projects into the server via their terminals. This input data is uploaded to the server as a text file containing the specifications.

[0501] Step 2:

[0502] The server uses spaCy to analyze the input specification text using natural language processing. This extracts important requirements and keywords from the specification. The input is the text data of the specification, and the output is a list of extracted requirements and keywords.

[0503] Step 3:

[0504] The server references an SQL database to search for proposal data from similar past projects. This identifies common elements from past success stories. The input is a list of extracted requirements, and the output is the past case data found.

[0505] Step 4:

[0506] The server uses a generative AI model to automatically generate documents. This creates a proposal that includes optimal suggestions regarding environmental and resource management. The input is requirements and data from past cases, and the output is the generated proposal document data.

[0507] Step 5:

[0508] The user reviews the generated proposal via the terminal and makes revisions as needed. The input is the generated proposal, and the output is the final version of the proposal reviewed by the user.

[0509] Step 6:

[0510] After the project progresses, the server automatically generates a work breakdown diagram and manages resource allocation based on it. The input is the final proposal, and the output is the configuration diagram and resource management plan.

[0511] Step 7:

[0512] The server uses pm4py to monitor project progress in real time and automatically sends alerts to the user when delays or risks are detected. The input is project progress data, and the output is alert information for the user.

[0513] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0514] This invention combines a system for efficiently and effectively creating proposals for bidding projects by public institutions and corporations with an emotion engine that utilizes user emotions. Specific embodiments of this system are described below.

[0515] In this system, the user first inputs the bid specifications into a terminal and transmits them to the system. The server analyzes this input data using natural language processing to extract the necessary requirements. Next, the server uses a database referencing mechanism to search the database of past bid proposals and identify and analyze similar cases. Based on this information, the server uses an automated document generation mechanism to create the optimal proposal.

[0516] The emotion engine recognizes the user's emotional state and adjusts the content and interface of the proposal based on that. For example, when a user reviews a proposal, the emotion engine uses cameras and sensors to analyze the user's facial expressions and voice, and based on the results, estimates the user's stress level and satisfaction level in real time.

[0517] Using this emotional data, the server dynamically modifies the interface to help users work more comfortably. For example, if a user is emotionally stressed, the system reduces the user's burden by adjusting the layout of proposals to make them easier to read or summarizing the information presented concisely.

[0518] Furthermore, using feedback from the emotion engine, the server makes suggestions to optimize communication among team members even during the project management phase. This process, when combined with real-time progress monitoring during project execution, improves the project's success rate.

[0519] As a concrete example of this system, consider a case where a company participates in a bid to build a large-scale IT system. The server extracts the key points from the specifications and automatically generates a proposal based on past successful examples. At this time, if the emotion engine detects the user's tension or anxiety, it visually highlights important points in the proposal and makes adjustments to help the user understand it.

[0520] Thus, by integrating proposal creation and project management with emotional data, this invention not only improves efficiency but also enhances the user experience based on ergonomics.

[0521] The following describes the processing flow.

[0522] Step 1:

[0523] Users upload the bid specifications in electronic format to their terminals and input the data into the system. This is the starting point of the proposal creation process.

[0524] Step 2:

[0525] The server analyzes the uploaded bid specifications using natural language processing techniques, extracting key requirements and keywords from the specifications. This clarifies the project requirements.

[0526] Step 3:

[0527] The server uses database referencing to search the database of past bidding projects and identify similar projects and their success factors. In this process, it analyzes the characteristics and patterns of past successful proposals.

[0528] Step 4:

[0529] The server uses automated document generation methods to create an optimal proposal that highlights the company's competitive advantages, based on extracted requirements and historical data. The proposal includes project plans and details of technology provision.

[0530] Step 5:

[0531] The user reviews the generated proposal on their device, and the emotion engine acquires emotional data from the user's facial expressions and voice. It then evaluates stress and satisfaction levels and adjusts the interface as needed.

[0532] Step 6:

[0533] The server uses feedback from the emotion engine to dynamically adjust the content and interface of the proposal. For example, if a user experiences stress, improvements such as redisplaying information in a more concise manner are made.

[0534] Step 7:

[0535] After the proposal is completed, in preparation for the project being awarded, the server uses a work breakdown diagram generation mechanism to visually define the project tasks and automatically determines the priority and resource allocation for each task.

[0536] Step 8:

[0537] After the project starts, the server monitors the project's progress in real time using progress monitoring tools and provides feedback using an emotion engine to improve team communication. Notifications are sent to the user as needed.

[0538] (Example 2)

[0539] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0540] In today's competitive environment, companies and public institutions need to prepare bid proposals quickly and effectively. However, proposal preparation is often complex and time-consuming, requiring the effective use of data from past projects and the provision of a user-friendly work environment. Traditional systems have struggled to comprehensively meet these requirements.

[0541] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0542] In this invention, the server includes a natural language processing means for analyzing text and extracting requirements, a database referencing means for analyzing similar cases by referring to past proposal data, an automatic document generation means for generating an optimal document based on the extracted requirements and analyzed data, an emotion engine means for recognizing the user's emotional state and dynamically adjusting the document content and operation screen based on the results, and a progress monitoring means for monitoring project progress in real time and providing notifications as needed. This enables an efficient and user-friendly proposal creation process and improves the effectiveness of project management.

[0543] "Natural language processing methods" are technologies that analyze input text data and extract specific requirements or information from it. Specifically, they obtain information through methods such as word tokenization, part-of-speech tagging, and semantic analysis.

[0544] A "database referencing method" refers to a technique or technology for extracting and analyzing necessary information from storage devices that hold historical data. It is used when searching for and analyzing similar cases.

[0545] An "automatic document generation method" is a technology for automatically generating documents with a specific format and content based on input data. It can be used to create proposals and other documents using natural language generation technology.

[0546] An "emotional engine" is a system that analyzes data such as the user's facial expressions and voice to infer the user's emotional state. Based on this information, it is possible to adjust the interface and change the way documents are presented.

[0547] "Progress monitoring means" refers to technologies and tools for tracking project progress in real time and providing necessary notifications and feedback. They have the function of continuously monitoring the project towards its success.

[0548] This invention provides a system for companies and public institutions to smoothly and effectively create bid proposals and manage projects. Users input bid specifications into their terminals and transfer the digital data to a server. The server analyzes the specifications using natural language processing and extracts the necessary requirements. For this natural language processing, Python's NLTK and spaCy are used as the software to rely on.

[0549] Next, the server uses a database lookup mechanism to search a database containing past similar cases. Common SQL servers or NoSQL databases are often used for database management. Based on the retrieved information, the server uses a generative AI model to automatically generate the optimal proposal. Examples of generative AI models used here include large-scale language models.

[0550] Furthermore, the emotion engine analyzes the user's facial expressions and voice in real time as they review proposals. This utilizes camera sensors and microphones, employing facial recognition APIs and voice analysis tools. Based on the emotion data, the server dynamically adjusts the interface display to support a comfortable user experience. If the user is experiencing stress, the document layout can be adjusted, and important information can be highlighted.

[0551] As a concrete example, consider a case where an organization participates in a bid to build a large-scale IT system. The server analyzes the specifications and generates an optimal proposal based on past successes. Then, content adjustments are made to accommodate the user's preferences. With such a system, the user can obtain efficient and high-quality results in proposal creation.

[0552] Examples of prompt messages include: "Based on the following specifications, please generate a company bid proposal, referencing past success stories. Consider user sentiment data and highlight key points." This information allows users to make quick decisions and increase their chances of successful bidding.

[0553] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0554] Step 1:

[0555] The user enters the bidding specifications into a terminal and sends the digital data to the server. In this input step, the specifications are usually uploaded in PDF or Word format and transferred to the server. As output, the digital data of the bidding specifications is saved on the server.

[0556] Step 2:

[0557] The server analyzes the received bid specifications using natural language processing. Specifically, it tokenizes the input text data, tags it with parts of speech, and extracts important requirements from the specifications. The input is digital data sent from the terminal, and the output is a list of requirements.

[0558] Step 3:

[0559] The server references past proposal data and uses database lookup mechanisms to analyze similar cases. It issues SQL queries to extract highly relevant cases and analyzes their success factors. The input is a list of extracted requirements, and the output is the analysis results of similar cases.

[0560] Step 4:

[0561] The server uses a generation AI model to automatically generate documents based on extracted requirements and analysis results. It generates the optimal proposal using prompt messages. The input is the analysis results of similar cases, and the output is a draft proposal. These prompt messages are sent to the generation AI model in the format of "Please generate a proposal based on the following specifications, referring to past successful cases."

[0562] Step 5:

[0563] When a user reviews a proposal, the emotion engine analyzes the user's facial expressions and voice. Based on data collected by cameras and microphones, it infers the user's emotional state. The input is real-time data from the user, and the output is an evaluation of their emotional state.

[0564] Step 6:

[0565] The server dynamically adjusts the content of the proposal and the user interface based on an assessment of the user's emotional state. For example, if the user is feeling stressed, the document layout is changed to make it easier to read. The input is an assessment of the user's emotional state, and the output is the adjusted interface and proposal.

[0566] (Application Example 2)

[0567] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0568] Proposal creation for bidding and project management requires efficiency and effectiveness, as well as flexibility that takes into account human emotions. However, existing systems have problems with insufficient interface adjustments that reflect user emotions and optimization of work efficiency. Therefore, there is a need for technology that improves proposal creation and project progress management while appropriately utilizing user emotions.

[0569] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0570] In this invention, the server includes a language analysis means for analyzing text and extracting requirements, a memory reference means for analyzing similar cases by referring to past proposal information, and an emotion recognition means for detecting the emotional state of the worker and dynamically adjusting work procedures and information presentation based on that emotion. This enables the automatic generation of proposals tailored to the user's emotions and project management in a low-stress environment.

[0571] "Linguistic analysis means" refers to techniques for analyzing input text and extracting structural requirements.

[0572] The "memory device reference means" is a function for searching previously accumulated proposal information and identifying and analyzing similar cases.

[0573] "Automated document creation method" refers to a technology that generates the optimal proposal based on analyzed requirements and similar cases.

[0574] The "diagram generation means" is a function for generating a diagram that visually breaks down project tasks.

[0575] "Monitoring means" refers to technology for monitoring the progress of work in real time and transmitting information as needed.

[0576] "Emotion recognition means" refers to technology that detects the emotional state of a worker from their facial expressions and voice, and adjusts work procedures and information presentation accordingly.

[0577] In this embodiment of the invention, the server uses language analysis means to extract requirements from text entered by the user into the terminal. Furthermore, the storage device reference means identifies and analyzes similar cases based on past proposal information. This enables the automatic creation of the optimal document. In addition, the emotion recognition means detects the emotional state of the worker and dynamically adjusts the work procedure and information presentation as needed.

[0578] The hardware consists of terminal devices equipped with cameras and emotion sensors, while the software includes language analysis libraries for natural language processing and speech analysis software for emotion recognition. Specifically, Python emotion recognition libraries and natural language processing tools are examples. Using these, the server performs data processing and calculations, enabling users to work without stress.

[0579] A concrete example of this system is a factory production line where workers use camera-equipped terminals. When a worker is referring to instructions on how to set up a machine, the system can detect the worker's frustration and automatically simplify the display of procedures and information.

[0580] Example of a prompt:

[0581] "Adjust the procedures for completing the designated process according to the stress levels of the workers."

[0582] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0583] Step 1:

[0584] The server receives text entered by the user on the terminal and extracts requirements using language analysis tools. The input for this step is the text entered by the user, and the output is the extracted requirements. This process uses natural language processing algorithms to understand the context and identify the necessary requirements.

[0585] Step 2:

[0586] The server uses a memory access mechanism to search for previously stored proposal information and identifies and analyzes cases similar to the input requirements. The input for this step is the requirements extracted in step 1, and the output is the analysis results of similar cases. A database query is executed to extract relevant proposal data.

[0587] Step 3:

[0588] The server uses an automated document generation system to generate an optimal proposal based on the outputs of Step 1 and Step 2. The input for this step is the analysis results of requirements and similar cases, and the output is a draft proposal. A generative AI model is utilized to generate the document in natural language.

[0589] Step 4:

[0590] The device detects the user's emotional state through its camera and sensors and transmits it to the server. The input for this step is data from the user's facial expressions and voice, and the output is the evaluation of their emotional state. Voice and image analysis software is used to evaluate the emotions.

[0591] Step 5:

[0592] The server adjusts the presentation method and content of the proposal based on the results of the emotion recognition system. The input for this step is the result of the emotional state evaluation, and the output is the adjusted information presentation. For example, if the user is feeling stressed, the layout is changed to highlight important points.

[0593] Step 6:

[0594] The user reviews the proposal provided on the terminal and makes any necessary revisions. The input for this step is the revised proposal, and the output is the final proposal. Revisions are made through a simple drag-and-drop interface.

[0595] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0596] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0597] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0598] [Fourth Embodiment]

[0599] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0600] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0601] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0602] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0603] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0604] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0605] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0606] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0607] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0608] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0609] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0610] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0611] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0612] This invention provides a method for streamlining proposal creation and project management using an integrated AI system specifically designed for bidding projects by public institutions and corporations. Specific embodiments of the system are described below.

[0613] First, the user inputs information into the system via a terminal, based on the bidding specifications provided by the public institution. This initiates the proposal creation process.

[0614] The server analyzes the received specifications using natural language processing to extract the most important requirements and keywords. In this process, it extracts technical requirements and readily usable functions, and also analyzes interface specifications for integration with other systems.

[0615] Next, the server uses a database of past bidding projects to search for similar projects and identify common elements of successful proposals. This makes it possible to find key points and effective strategies to include in a new proposal.

[0616] Next, the server uses this information to generate a proposal that highlights the company's resources and technical capabilities using an automated document generation system. This proposal will specifically outline the project's objectives, methodology, timeline, and the company's competitive advantages.

[0617] This proposal is reviewed by the user via their terminal, and revisions are made as needed. This process ensures that the most persuasive and optimal proposal is finalized. In addition, if the proposal is accepted, the server will initiate project management by configuring tasks via a work breakdown diagram generation mechanism, prioritizing each task, and allocating corresponding resources.

[0618] As the project progresses, the server tracks its progress in real time using progress monitoring tools. If delays or risks are detected in the progress according to pre-defined criteria, the server sends an alert to the user to prompt a quick response.

[0619] As a concrete example, consider a case where an IT company participates in a bid for a "data management system development project." The server extracts requirements such as "cloud technology," "high availability," and "scalability" from the specifications, and identifies elements such as "rapid data migration" and "completion within budget" from past success stories. Based on these, it creates a proposal and automatically formulates a project management plan.

[0620] This invention enables companies to efficiently handle bidding projects and significantly improve the accuracy of project management.

[0621] The following describes the processing flow.

[0622] Step 1:

[0623] Users upload the bidding specifications provided by public institutions in electronic format to their terminals and input the data into the system.

[0624] Step 2:

[0625] The server analyzes the bid specifications received from the user using natural language processing techniques and extracts key requirements and keywords from the specifications. For example, it identifies technical requirements and project objectives.

[0626] Step 3:

[0627] The server uses database referencing to search the database of past bids and identify bids similar to the requirements of the extracted specifications. It then analyzes commonalities in the strategies and proposals of past successful bids.

[0628] Step 4:

[0629] Based on extracted requirements and historical data, the server uses automated document generation to create a proposal that effectively showcases the company's resources and technology. The generated proposal clearly outlines the project's progress and the roles and responsibilities of the employees.

[0630] Step 5:

[0631] The user reviews the proposal generated by the server on their terminal, makes manual corrections or additional comments as needed, and then finalizes the proposal.

[0632] Step 6:

[0633] After the proposal is accepted, the server uses a work breakdown diagram generation tool to visually define each task in the project and automatically determine its timeline and resource allocation.

[0634] Step 7:

[0635] The server uses progress monitoring tools to track project status in real time during project execution. If progress is behind schedule or a risk arises, it sends appropriate notifications to the user to prompt action.

[0636] (Example 1)

[0637] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0638] Public institutions and corporations face challenges in the efficiency of proposal preparation and project management when participating in bidding processes. Manual requirements analysis and searching for similar projects are time-consuming and labor-intensive, and progress monitoring during project execution is insufficient. Furthermore, optimizing resource allocation is difficult, potentially impairing the overall performance of the project.

[0639] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0640] In this invention, the server includes information processing means for analyzing text and extracting requirements, data retrieval means for analyzing similar cases by referring to past case data, and document creation means for generating an optimal document based on the extracted requirements and analyzed data. This makes it possible to streamline the proposal creation and project management processes and improve a company's bidding activities and project execution capabilities.

[0641] "Information processing means" refers to technology for analyzing input text data and extracting necessary requirements.

[0642] A "data retrieval method" is a method for identifying and analyzing similar cases by referring to a database of past cases.

[0643] A "document creation method" is a system that automatically generates optimal proposals and documents based on analyzed requirements and data.

[0644] A "diagram generation method" is a technique that breaks down a project into smaller business units and creates diagrams that show the flow and relationships of each business unit.

[0645] A "progress management system" is a function that monitors the progress of a project in real time and notifies users if there are any problems.

[0646] "Resource allocation methods" refer to methods for allocating a company's resources in the most optimal way, based on project requirements.

[0647] An "operation screen" is an interface that allows users to interact with the system and review and modify documents.

[0648] This invention is an integrated system for public institutions and corporations to streamline the creation of proposals and project management for bidding projects. The system comprises information processing means, data retrieval means, document creation means, configuration diagram generation means, progress management means, resource allocation means, and an operation screen.

[0649] First, the user inputs the bidding specifications provided by the public institution into their terminal. The terminal used is a standard computer or tablet device, and the specifications are uploaded in PDF or Word file format.

[0650] The server analyzes the input text data using natural language processing technology. Specifically, it uses software such as SpaCy and NLTK for natural language processing to extract important requirements and keywords. This information processing method makes it easier to identify particularly noteworthy technical and functional requirements within the specifications.

[0651] Next, the server references a database of past cases to identify and analyze similar cases. Using an SQL database, it extracts common elements from past success stories to help create new proposals. By listing similar items and strategies based on the retrieved data, the quality of the proposal is improved.

[0652] The server automatically generates proposals using a generative AI model. For example, it can use OpenAI's GPT model to generate persuasive proposals that highlight a company's resources and technical capabilities. These proposals specifically describe the project's objectives, methodology, timeline, and the company's competitive advantages.

[0653] The generated proposal can be reviewed by the user through an operation screen, and modifications can be made as needed. This operation screen allows the user to manually edit each part of the proposal and confirm the final content.

[0654] If the bid is successful, the server will begin project management and generate a diagram to break down the project into smaller operational units. Project management tools will be used to prioritize and allocate resources to each task, thereby improving operational efficiency.

[0655] During the actual project, the server monitors the project's progress in real time using progress management tools. If delays or risks occur in the progress, the server automatically sends warnings and notifications to the user to prompt a quick response.

[0656] A concrete example is the subject matter of "Tender specifications for the development of a data management system utilizing cloud technology." In this case, a suitable example of a prompt would be, "Generate a proposal based on the following tender specifications: Submit a detailed plan for a project utilizing 'cloud technology'."

[0657] This invention allows companies to drastically streamline the bidding process and significantly improve the effectiveness and efficiency of project management.

[0658] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0659] Step 1:

[0660] The user inputs the bidding specifications provided by the public institution into the terminal. Specifically, they upload the specifications as a PDF or Word file to a dedicated form. The entered data is sent to the system, and it is ready for natural language processing.

[0661] Step 2:

[0662] The server analyzes specification data using a natural language processing engine. Text data is provided as input. This process uses SpaCy or NLTK to tokenize the text and extract key requirements and keywords. This makes it easier to identify technical and functional requirements within the project. The output is a list of extracted requirements.

[0663] Step 3:

[0664] The server references a database of past cases based on the extracted requirements. The input data is the extracted list of requirements. Using an SQL database, it filters similar cases and lists successful examples. This gathers data useful for new proposals. The output is a list of similar cases and their common elements.

[0665] Step 4:

[0666] The server generates a proposal using data from similar projects. The input data consists of a requirements list and elements from similar projects. It utilizes a generation AI model (e.g., a GPT model) to automatically create a proposal that highlights the company's advantages. Specifically, it converts the input data into prompt sentences and feeds them into the AI ​​to generate the document. The output is the automatically generated proposal.

[0667] Step 5:

[0668] The user reviews and modifies the proposal on the user interface. The input data is an automatically generated proposal. The user opens the proposal in a word processor, checks its contents, and manually edits it as needed. Specific actions include correcting text and inserting additional information. The output is the revised proposal.

[0669] Step 6:

[0670] The server begins project management once the proposal is finalized. The input data is the completed proposal. Using a project management tool, it generates a Work Breakdown Structure (WBS) and structures the tasks. Specifically, it prioritizes each task and allocates the necessary resources. The output is a project plan and a list of tasks.

[0671] Step 7:

[0672] The server monitors project progress in real time during the project's execution. The input data is project progress information. Using progress monitoring tools, it tracks ongoing tasks and notifies the user if delays or risks occur. Specific actions include evaluating progress and issuing alerts. The output is delay and risk alert information.

[0673] (Application Example 1)

[0674] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0675] Modern public works and infrastructure projects face increasing complexity in the bidding process and the need for efficient management from the proposal stage to project management. However, traditional methods make it difficult to process vast amounts of information and create proposals that appropriately consider the environment and resources, which is a cause of project delays and failures.

[0676] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0677] In this invention, the server includes a natural language processing means for analyzing text and extracting requirements, a database referencing means for analyzing similar cases by referring to past proposal data, and an automated document generation means for generating an optimal proposal based on the extracted requirements and analyzed data. This enables more efficient proposal creation in public works and infrastructure projects, and optimal allocation of resources in project management.

[0678] "Natural language processing tools" are technologies that analyze text and extract important requirements and keywords from it.

[0679] A "database referencing method" is a technology for searching past proposal data and analyzing similar cases.

[0680] An "automatic document generation method" is a technology that has the function of automatically creating an optimal proposal based on extracted requirements and analyzed data.

[0681] The "configuration diagram generation method" is a technology that breaks down project work in detail after receiving an order, enabling efficient management of the work.

[0682] A "progress monitoring system" is a technology that monitors the progress of a project in real time and provides appropriate notifications according to pre-set criteria.

[0683] "An automated system for creating public works proposals" refers to a technology that quickly and effectively generates proposals while taking into account the specific environmental requirements associated with public works projects.

[0684] A "resource management support configuration" refers to a technology that supports the efficient management and allocation of resources based on project requirements.

[0685] The system for realizing this invention consists of a series of program modules that run on a cloud server. The server is based on Python and uses spaCy and Transformers as natural language processing libraries. This enables natural language processing to extract important requirements from bidding documents for public projects. A SQL-based database is used for database lookups, allowing for high-speed retrieval of past proposal information.

[0686] Automated document generation is performed using a generation AI model based on this extracted and analyzed data, and the proposal reflects environmental requirements and the streamlining of resource management. This process utilizes a database of past project success stories.

[0687] Users access the generated proposals via an interface that allows them to review and modify them as needed, using their terminals. This interface is provided through a user-friendly GUI. As the project progresses, the server automatically generates work breakdown diagrams and manages resource allocation. Real-time progress monitoring is performed using the project management library pm4py, and alerts are automatically sent to the user if progress is behind schedule.

[0688] For example, if a city is bidding on the "implementation of a sustainable energy system," the server can identify key requirements related to energy efficiency from the specifications and quickly create an optimal proposal based on past success stories.

[0689] As an example of a prompt message for a generative AI,

[0690] "To create a proposal for a smart city project, please analyze the bidding specifications, extract key information, and generate an optimal proposal based on past successful case studies."

[0691] These are some examples.

[0692] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0693] Step 1:

[0694] Users input the bidding specifications for public projects into the server via their terminals. This input data is uploaded to the server as a text file containing the specifications.

[0695] Step 2:

[0696] The server uses spaCy to analyze the input specification text using natural language processing. This extracts important requirements and keywords from the specification. The input is the text data of the specification, and the output is a list of extracted requirements and keywords.

[0697] Step 3:

[0698] The server references an SQL database to search for proposal data from similar past projects. This identifies common elements from past success stories. The input is a list of extracted requirements, and the output is the past case data found.

[0699] Step 4:

[0700] The server uses a generative AI model to automatically generate documents. This creates a proposal that includes optimal suggestions regarding environmental and resource management. The input is requirements and data from past cases, and the output is the generated proposal document data.

[0701] Step 5:

[0702] The user reviews the generated proposal via the terminal and makes revisions as needed. The input is the generated proposal, and the output is the final version of the proposal reviewed by the user.

[0703] Step 6:

[0704] After the project progresses, the server automatically generates a work breakdown diagram and manages resource allocation based on it. The input is the final proposal, and the output is the configuration diagram and resource management plan.

[0705] Step 7:

[0706] The server uses pm4py to monitor project progress in real time and automatically sends alerts to the user when delays or risks are detected. The input is project progress data, and the output is alert information for the user.

[0707] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0708] This invention combines a system for efficiently and effectively creating proposals for bidding projects by public institutions and corporations with an emotion engine that utilizes user emotions. Specific embodiments of this system are described below.

[0709] In this system, the user first inputs the bid specifications into a terminal and transmits them to the system. The server analyzes this input data using natural language processing to extract the necessary requirements. Next, the server uses a database referencing mechanism to search the database of past bid proposals and identify and analyze similar cases. Based on this information, the server uses an automated document generation mechanism to create the optimal proposal.

[0710] The emotion engine recognizes the user's emotional state and adjusts the content and interface of the proposal based on that. For example, when a user reviews a proposal, the emotion engine uses cameras and sensors to analyze the user's facial expressions and voice, and based on the results, estimates the user's stress level and satisfaction level in real time.

[0711] Using this emotional data, the server dynamically modifies the interface to help users work more comfortably. For example, if a user is emotionally stressed, the system reduces the user's burden by adjusting the layout of proposals to make them easier to read or summarizing the information presented concisely.

[0712] Furthermore, using feedback from the emotion engine, the server makes suggestions to optimize communication among team members even during the project management phase. This process, when combined with real-time progress monitoring during project execution, improves the project's success rate.

[0713] As a concrete example of this system, consider a case where a company participates in a bid to build a large-scale IT system. The server extracts the key points from the specifications and automatically generates a proposal based on past successful examples. At this time, if the emotion engine detects the user's tension or anxiety, it visually highlights important points in the proposal and makes adjustments to help the user understand it.

[0714] Thus, by integrating proposal creation and project management with emotional data, this invention not only improves efficiency but also enhances the user experience based on ergonomics.

[0715] The following describes the processing flow.

[0716] Step 1:

[0717] Users upload the bid specifications in electronic format to their terminals and input the data into the system. This is the starting point of the proposal creation process.

[0718] Step 2:

[0719] The server analyzes the uploaded bid specifications using natural language processing techniques, extracting key requirements and keywords from the specifications. This clarifies the project requirements.

[0720] Step 3:

[0721] The server uses database referencing to search the database of past bidding projects and identify similar projects and their success factors. In this process, it analyzes the characteristics and patterns of past successful proposals.

[0722] Step 4:

[0723] The server uses automated document generation methods to create an optimal proposal that highlights the company's competitive advantages, based on extracted requirements and historical data. The proposal includes project plans and details of technology provision.

[0724] Step 5:

[0725] The user reviews the generated proposal on their device, and the emotion engine acquires emotional data from the user's facial expressions and voice. It then evaluates stress and satisfaction levels and adjusts the interface as needed.

[0726] Step 6:

[0727] The server uses feedback from the emotion engine to dynamically adjust the content and interface of the proposal. For example, if a user experiences stress, improvements such as redisplaying information in a more concise manner are made.

[0728] Step 7:

[0729] After the proposal is completed, in preparation for the project being awarded, the server uses a work breakdown diagram generation mechanism to visually define the project tasks and automatically determines the priority and resource allocation for each task.

[0730] Step 8:

[0731] After the project starts, the server monitors the project's progress in real time using progress monitoring tools and provides feedback using an emotion engine to improve team communication. Notifications are sent to the user as needed.

[0732] (Example 2)

[0733] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0734] In today's competitive environment, companies and public institutions need to prepare bid proposals quickly and effectively. However, proposal preparation is often complex and time-consuming, requiring the effective use of data from past projects and the provision of a user-friendly work environment. Traditional systems have struggled to comprehensively meet these requirements.

[0735] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0736] In this invention, the server includes a natural language processing means for analyzing text and extracting requirements, a database referencing means for analyzing similar cases by referring to past proposal data, an automatic document generation means for generating an optimal document based on the extracted requirements and analyzed data, an emotion engine means for recognizing the user's emotional state and dynamically adjusting the document content and operation screen based on the results, and a progress monitoring means for monitoring project progress in real time and providing notifications as needed. This enables an efficient and user-friendly proposal creation process and improves the effectiveness of project management.

[0737] "Natural language processing methods" are technologies that analyze input text data and extract specific requirements or information from it. Specifically, they obtain information through methods such as word tokenization, part-of-speech tagging, and semantic analysis.

[0738] A "database referencing method" refers to a technique or technology for extracting and analyzing necessary information from storage devices that hold historical data. It is used when searching for and analyzing similar cases.

[0739] An "automatic document generation method" is a technology for automatically generating documents with a specific format and content based on input data. It can be used to create proposals and other documents using natural language generation technology.

[0740] An "emotional engine" is a system that analyzes data such as the user's facial expressions and voice to infer the user's emotional state. Based on this information, it is possible to adjust the interface and change the way documents are presented.

[0741] "Progress monitoring means" refers to technologies and tools for tracking project progress in real time and providing necessary notifications and feedback. They have the function of continuously monitoring the project towards its success.

[0742] This invention provides a system for companies and public institutions to smoothly and effectively create bid proposals and manage projects. Users input bid specifications into their terminals and transfer the digital data to a server. The server analyzes the specifications using natural language processing and extracts the necessary requirements. For this natural language processing, Python's NLTK and spaCy are used as the software to rely on.

[0743] Next, the server uses a database lookup mechanism to search a database containing past similar cases. Common SQL servers or NoSQL databases are often used for database management. Based on the retrieved information, the server uses a generative AI model to automatically generate the optimal proposal. Examples of generative AI models used here include large-scale language models.

[0744] Furthermore, the emotion engine analyzes the user's facial expressions and voice in real time as they review proposals. This utilizes camera sensors and microphones, employing facial recognition APIs and voice analysis tools. Based on the emotion data, the server dynamically adjusts the interface display to support a comfortable user experience. If the user is experiencing stress, the document layout can be adjusted, and important information can be highlighted.

[0745] As a concrete example, consider a case where an organization participates in a bid to build a large-scale IT system. The server analyzes the specifications and generates an optimal proposal based on past successes. Then, content adjustments are made to accommodate the user's preferences. With such a system, the user can obtain efficient and high-quality results in proposal creation.

[0746] Examples of prompt messages include: "Based on the following specifications, please generate a company bid proposal, referencing past success stories. Consider user sentiment data and highlight key points." This information allows users to make quick decisions and increase their chances of successful bidding.

[0747] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0748] Step 1:

[0749] The user enters the bidding specifications into a terminal and sends the digital data to the server. In this input step, the specifications are usually uploaded in PDF or Word format and transferred to the server. As output, the digital data of the bidding specifications is saved on the server.

[0750] Step 2:

[0751] The server analyzes the received bid specifications using natural language processing. Specifically, it tokenizes the input text data, tags it with parts of speech, and extracts important requirements from the specifications. The input is digital data sent from the terminal, and the output is a list of requirements.

[0752] Step 3:

[0753] The server references past proposal data and uses database lookup mechanisms to analyze similar cases. It issues SQL queries to extract highly relevant cases and analyzes their success factors. The input is a list of extracted requirements, and the output is the analysis results of similar cases.

[0754] Step 4:

[0755] The server uses a generation AI model to automatically generate documents based on extracted requirements and analysis results. It generates the optimal proposal using prompt messages. The input is the analysis results of similar cases, and the output is a draft proposal. These prompt messages are sent to the generation AI model in the format of "Please generate a proposal based on the following specifications, referring to past successful cases."

[0756] Step 5:

[0757] When a user reviews a proposal, the emotion engine analyzes the user's facial expressions and voice. Based on data collected by cameras and microphones, it infers the user's emotional state. The input is real-time data from the user, and the output is an evaluation of their emotional state.

[0758] Step 6:

[0759] The server dynamically adjusts the content of the proposal and the user interface based on an assessment of the user's emotional state. For example, if the user is feeling stressed, the document layout is changed to make it easier to read. The input is an assessment of the user's emotional state, and the output is the adjusted interface and proposal.

[0760] (Application Example 2)

[0761] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0762] Proposal creation for bidding and project management requires efficiency and effectiveness, as well as flexibility that takes into account human emotions. However, existing systems have problems with insufficient interface adjustments that reflect user emotions and optimization of work efficiency. Therefore, there is a need for technology that improves proposal creation and project progress management while appropriately utilizing user emotions.

[0763] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0764] In this invention, the server includes a language analysis means for analyzing text and extracting requirements, a memory reference means for analyzing similar cases by referring to past proposal information, and an emotion recognition means for detecting the emotional state of the worker and dynamically adjusting work procedures and information presentation based on that emotion. This enables the automatic generation of proposals tailored to the user's emotions and project management in a low-stress environment.

[0765] "Linguistic analysis means" refers to techniques for analyzing input text and extracting structural requirements.

[0766] The "memory device reference means" is a function for searching previously accumulated proposal information and identifying and analyzing similar cases.

[0767] "Automated document creation method" refers to a technology that generates the optimal proposal based on analyzed requirements and similar cases.

[0768] The "diagram generation means" is a function for generating a diagram that visually breaks down project tasks.

[0769] "Monitoring means" refers to technology for monitoring the progress of work in real time and transmitting information as needed.

[0770] "Emotion recognition means" refers to technology that detects the emotional state of a worker from their facial expressions and voice, and adjusts work procedures and information presentation accordingly.

[0771] In this embodiment of the invention, the server uses language analysis means to extract requirements from text entered by the user into the terminal. Furthermore, the storage device reference means identifies and analyzes similar cases based on past proposal information. This enables the automatic creation of the optimal document. In addition, the emotion recognition means detects the emotional state of the worker and dynamically adjusts the work procedure and information presentation as needed.

[0772] The hardware consists of terminal devices equipped with cameras and emotion sensors, while the software includes language analysis libraries for natural language processing and speech analysis software for emotion recognition. Specifically, Python emotion recognition libraries and natural language processing tools are examples. Using these, the server performs data processing and calculations, enabling users to work without stress.

[0773] A concrete example of this system is a factory production line where workers use camera-equipped terminals. When a worker is referring to instructions on how to set up a machine, the system can detect the worker's frustration and automatically simplify the display of procedures and information.

[0774] Example of a prompt:

[0775] "Adjust the procedures for completing the designated process according to the stress levels of the workers."

[0776] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0777] Step 1:

[0778] The server receives text entered by the user on the terminal and extracts requirements using language analysis tools. The input for this step is the text entered by the user, and the output is the extracted requirements. This process uses natural language processing algorithms to understand the context and identify the necessary requirements.

[0779] Step 2:

[0780] The server uses a memory access mechanism to search for previously stored proposal information and identifies and analyzes cases similar to the input requirements. The input for this step is the requirements extracted in step 1, and the output is the analysis results of similar cases. A database query is executed to extract relevant proposal data.

[0781] Step 3:

[0782] The server uses an automated document generation system to generate an optimal proposal based on the outputs of Step 1 and Step 2. The input for this step is the analysis results of requirements and similar cases, and the output is a draft proposal. A generative AI model is utilized to generate the document in natural language.

[0783] Step 4:

[0784] The device detects the user's emotional state through its camera and sensors and transmits it to the server. The input for this step is data from the user's facial expressions and voice, and the output is the evaluation of their emotional state. Voice and image analysis software is used to evaluate the emotions.

[0785] Step 5:

[0786] The server adjusts the presentation method and content of the proposal based on the results of the emotion recognition system. The input for this step is the result of the emotional state evaluation, and the output is the adjusted information presentation. For example, if the user is feeling stressed, the layout is changed to highlight important points.

[0787] Step 6:

[0788] The user reviews the proposal provided on the terminal and makes any necessary revisions. The input for this step is the revised proposal, and the output is the final proposal. Revisions are made through a simple drag-and-drop interface.

[0789] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0790] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0791] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0792] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0793] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0794] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0795] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0796] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0797] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0798] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0799] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0800] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0801] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0802] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0803] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0804] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0805] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0806] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0807] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0808] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0809] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0810] The following is further disclosed regarding the embodiments described above.

[0811] (Claim 1)

[0812] A natural language processing method that analyzes text and extracts requirements,

[0813] A database reference means for analyzing similar cases by referring to past proposal data,

[0814] An automated document generation means that generates an optimal proposal based on extracted requirements and analyzed data,

[0815] A means for generating a work breakdown diagram for breaking down project tasks after receiving an order,

[0816] A progress monitoring system that monitors project progress in real time and provides notifications as needed,

[0817] A system that includes this.

[0818] (Claim 2)

[0819] The system according to claim 1, comprising an interface for the user to review and revise an automatically generated proposal.

[0820] (Claim 3)

[0821] The system according to claim 1, comprising a resource allocation means for optimally allocating a company's resources based on the requirements of the bidding specifications.

[0822] "Example 1"

[0823] (Claim 1)

[0824] An information processing means for analyzing text and extracting requirements,

[0825] A data search method that analyzes similar cases by referring to past case data,

[0826] A document creation means that generates an optimal document based on extracted requirements and analyzed data,

[0827] A means for generating a configuration diagram to break down the work after receiving an order,

[0828] A progress management system that monitors the progress of tasks in real time and provides notifications as needed,

[0829] A resource allocation method that optimally allocates a company's resources based on the input data,

[0830] A system that includes this.

[0831] (Claim 2)

[0832] The system according to claim 1, further comprising an operation screen for the user to review and modify automatically generated documents.

[0833] (Claim 3)

[0834] The system according to claim 1, comprising means for generating a document that highlights the advantages of a company based on the input specifications.

[0835] "Application Example 1"

[0836] (Claim 1)

[0837] A natural language processing method that analyzes text and extracts requirements,

[0838] A database reference means for analyzing similar cases by referring to past proposal data,

[0839] An automated document generation means that generates an optimal proposal based on extracted requirements and analyzed data,

[0840] A means for generating a configuration diagram to break down project work after receiving an order,

[0841] A progress monitoring system that monitors the project's progress in real time and provides notifications according to established criteria,

[0842] A configuration that automates the creation of proposals for public works projects that take environmental requirements into consideration,

[0843] A configuration that supports efficient resource management tailored to project requirements,

[0844] A system that includes this.

[0845] (Claim 2)

[0846] The system according to claim 1, comprising means for the user to review and revise an automatically generated proposal.

[0847] (Claim 3)

[0848] The system according to claim 1, comprising means for optimizing information for public infrastructure projects.

[0849] "Example 2 of combining an emotion engine"

[0850] (Claim 1)

[0851] A natural language processing method that analyzes text and extracts requirements,

[0852] A database reference means for analyzing similar cases by referring to past proposal data,

[0853] An automated document generation means that generates an optimal document based on extracted requirements and analyzed data,

[0854] An emotion engine means that recognizes the user's emotional state and dynamically adjusts the document content and operation screen based on the results,

[0855] A progress monitoring system that monitors project progress in real time and provides notifications as needed,

[0856] A system that includes this.

[0857] (Claim 2)

[0858] The system according to claim 1, comprising an interface in which a user reviews an automatically generated document and is offered revisions based on sentiment data.

[0859] (Claim 3)

[0860] The system according to claim 1, comprising a planning and allocation means for optimally allocating the organization's resources based on extracted requirements.

[0861] "Application example 2 when combining with an emotional engine"

[0862] (Claim 1)

[0863] A language analysis tool that analyzes text and extracts requirements,

[0864] A memory reference means for analyzing similar cases by referring to past proposal information,

[0865] An automated document creation means that generates the optimal document based on extracted requirements and analyzed information,

[0866] A means for generating diagrams that break down the work content,

[0867] A monitoring system that monitors the progress in real time and transmits information as needed,

[0868] An emotion recognition means that detects the emotional state of a worker and dynamically adjusts work procedures and information presentation based on that emotion,

[0869] A system that includes this.

[0870] (Claim 2)

[0871] The system according to claim 1, further comprising a screen display unit for the user to review and modify automatically generated documents.

[0872] (Claim 3)

[0873] The system according to claim 1, comprising resource allocation means for optimally allocating the organization's resources based on the requirements of the specifications. [Explanation of symbols]

[0874] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A natural language processing method that analyzes text and extracts requirements, A database reference means for analyzing similar cases by referring to past proposal data, An automated document generation means that generates an optimal proposal based on extracted requirements and analyzed data, A means for generating a work breakdown diagram for breaking down project tasks after receiving an order, A progress monitoring system that monitors project progress in real time and provides notifications as needed, A system that includes this.

2. The system according to claim 1, further comprising an interface for the user to review and revise an automatically generated proposal.

3. The system according to claim 1, comprising a resource allocation means for optimally allocating a company's resources based on the requirements of the bidding specifications.

Images